Morphology based Galaxy Classification

Abstract

Galaxy evolution is an area of vital importance in current research as it is believed to hold vital clues of the past as well as the future of the universe. The structure or morphology of a galaxy acts as an indicator of its stage of evolution and may also shed light on the course of its future evolution. The deployment of high-resolution telescopes like James Webb Telescope has made available large amount of high-resolution images, thereby, facilitating the deployment of high-performance Machine Learning and Deep Learning techniques. In the proposed work, two different methods have been assessed to achieve better classification accuracy. The first work explores Zoom-Dilate Convolution and the second work explores equivariant convolution. In the first work, we have used cascaded simple Zoom- Dilate Convolution blocks to achieve most of the classification accuracy while transformer blocks are used to raise it further but not too much in order to keep the model reasonably lightweight. In the second work, we have explored equivariant convolution blocks to achieve most of our accuracy followed by a transformer block. The models have been trained on Galaxy10 SDSS datatset.